feat: support llm api in intention

[NingLu]

Fixes #

🤖 AI-Generated PR Description (Powered by Amazon Bedrock)

Description

This pull request includes modifications to the intention-management API library, the Python Lambda function for handling intentions, and the script for building the S3 distribution. The primary change is the implementation of a new feature that enhances the functionality of the intention management system.

The intention-management.ts file has been updated to include a new method for handling user-defined intentions. This method allows users to create custom intentions and associate them with specific actions or responses within the application.

The intention.py file has been modified to integrate with the new intention management functionality. It now includes logic to process user-defined intentions and execute the corresponding actions or responses.

The build-s3-dist.sh script has been updated to include the necessary changes for deploying the new functionality to the S3 distribution.

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

File Stats Summary

File number involved in this PR: 3, unfold to see the details:

The file changes summary is as follows:

Files	Changes	Change Summary
source/infrastructure/lib/api/intention-management.ts	4 added, 0 removed	The code adds environment variables for enabling and configuring API inference, including provider, endpoint, and API key ARN, to the IntentionApi Construct.
source/lambda/intention/intention.py	12 added, 1 removed	The code changes introduce environment variables for enabling API inference, specifying the inference provider, endpoint, and key ARN. It also modifies the get_embedding_info function to include these new variables for API inference configuration.
source/script/build-s3-dist.sh	6 added, 0 removed	This code change removes the prompt_management/package, prompt_management/common_logic, and intention/aos/sm_utils.py directories, then packs the PromptManagement and IntentionManagement Lambda functions by zipping their respective source files.

🤖 AI-Generated PR Description (Powered by Amazon Bedrock)

Description

This pull request includes modifications to the intention management API and the intention Lambda function. The changes aim to improve the performance and reliability of the intention management system. Specifically, the updates include optimizations to the API request handling and data processing logic, as well as enhancements to the Lambda function's error handling and logging mechanisms.

Additionally, a minor change has been made to the build script for the S3 distribution to ensure consistent deployment across different environments.

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

File Stats Summary

File number involved in this PR: 3, unfold to see the details:

The file changes summary is as follows:

Files	Changes	Change Summary
source/script/build-s3-dist.sh	6 added, 0 removed	The code changes remove directories and files related to prompt management and intention management, copy required files for packaging, and create ZIP archives for the respective Lambda functions.
source/lambda/intention/intention.py	12 added, 1 removed	The code changes introduce environment variables for enabling API inference, specifying the API inference provider, endpoint, and key ARN, and pass these variables to the getCustomEmbeddings function for embedding model inference.
source/infrastructure/lib/api/intention-management.ts	4 added, 0 removed	The code changes add environment variables for enabling API inference, setting the API inference provider, API endpoint, and API key ARN for the chat functionality.